Prediction device, prediction method, and prediction program

Abstract

A prediction device includes: an acquisition unit that acquires chemical substance information of a drug and pharmacological information of the drug; an estimation unit that estimates estimated information of the drug by performing machine learning using the chemical substance information and the pharmacological information; and an output unit that predicts and outputs both efficacy and side effects of the drug on an organism by retraining a model of the machine learning on the basis of the estimated information.

What is claimed is: 
     
         1 . A prediction device comprising:
 an acquisition unit that acquires chemical substance information of a drug and pharmacological information of the drug;   an estimation unit that estimates estimated information of the drug by performing machine learning using the chemical substance information and the pharmacological information; and   an output unit that predicts and outputs both efficacy and side effects of the drug on an organism by retraining a model of the machine learning on the basis of the estimated information.   
     
     
         2 . The prediction device according to  claim 1 , wherein
 the acquisition unit further acquires cellular level biological information of the drug, and   the estimation unit performs the machine learning using the chemical substance information, the pharmacological information, and the cellular level biological information.   
     
     
         3 . The prediction device according to  claim 1 , wherein the estimation unit estimates characteristic information of the drug on the basis of a chemical structure included in the chemical substance information and drug administration information included in the pharmacological information. 
     
     
         4 . The prediction device according to  claim 1 , wherein the estimation unit estimates pharmacokinetic information of the drug on the basis of a chemical structure included in the chemical substance information and drug administration information included in the pharmacological information. 
     
     
         5 . The prediction device according to  claim 2 , wherein the estimation unit estimates the cellular level biological information on the basis of a chemical structure included in the chemical substance information and drug administration information included in the pharmacological information. 
     
     
         6 . The prediction device according to  claim 3 , further comprising a preliminary estimation unit that preliminarily estimates the chemical structure of the drug on the basis of the characteristic information of the drug. 
     
     
         7 . The prediction device according to  claim 1 , wherein the estimation unit further retrains the model of the machine learning using other estimation information in predicting the estimated information. 
     
     
         8 . The prediction device according to  claim 1 , wherein the machine learning is a neural network and an autoencoder is used. 
     
     
         9 . The prediction device according to  claim 3 , wherein the chemical substance information of the drug includes chemical structure information and the characteristic information, the chemical structure information is a feature value on the basis of the chemical structure of the drug, and the characteristic information is a feature value on the basis of chemical and physical properties of the drug. 
     
     
         10 . The prediction device according to  claim 2 , wherein the cellular level biological information is a feature value on the basis of information on behavior of the drug when the drug is administered to a cultured cell. 
     
     
         11 . The prediction device according to  claim 3 , wherein the pharmacological information includes a feature value of the drug on the basis of its effect on an organism and its dynamics within a body as well as the drug administration information, which amount corresponds to a feature value on the basis of a drug administration method and biological information at a time of drug administration. 
     
     
         12 . The prediction device according to  claim 1 , wherein the output unit predicts and outputs a drug administration plan for the drug in predicting and outputting both the efficacy and side effects of the drug on an organism. 
     
     
         13 . The prediction device according to  claim 2 , wherein the acquisition unit includes a crawling unit that acquires at least either the chemical substance information of the drug, the cellular level biological information of the drug, or the pharmacological information of the drug from a website present on the Internet. 
     
     
         14 . A prediction method causing a computer to execute the steps of:
 acquiring chemical substance information of a drug and pharmacological information of the drug;   estimating estimated information of the drug by performing machine learning using the chemical substance information and the pharmacological information; and   predicting and outputting both efficacy and side effects of the drug on an organism by retraining a model of the machine learning on the basis of the estimated information.   
     
     
         15 . The prediction method according to  claim 14 , wherein
 the acquiring step further acquires cellular level biological information of the drug; and   the estimating step performs the machine learning using the chemical substance information, the pharmacological information, and the cellular level biological information.   
     
     
         16 . A non-transitory computer readable medium storing therein a prediction program causing a computer to embody:
 an acquisition function of acquiring chemical substance information of a drug and pharmacological information of the drug;   an estimation function of estimating estimated information of the drug by performing machine learning using the chemical substance information and the pharmacological information; and   an output function of predicting and outputting both efficacy and side effects of the drug on an organism by retraining a model of the machine learning on the basis of the estimated information.   
     
     
         17 . The non-transitory computer readable medium according to  claim 16 , wherein
 the acquisition function further acquires cellular level biological information of the drug, and   the estimation function performs the machine learning using the chemical substance information, the pharmacological information, and the cellular level biological information.